© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64786
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æį¢è¨Ģä¹ĭ
    -0.08
     numeric
    -0.07
    osa
    -0.07
    osit
    -0.07
     deliberately
    -0.07
    ool
    -0.07
    ÙĪØ®
    -0.07
    继èĢĮ
    -0.07
    ï¸ı
    -0.07
     âĢ¦
    -0.07
    POSITIVE LOGITS
    dba
    0.08
    çĮ
    0.08
    _NOTIFY
    0.07
     **,
    0.07
    Ñľ
    0.07
    -flash
    0.07
    æĽ´åĬłçļĦ
    0.07
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.07
    æĪij们就è¦ģ
    0.07
     ÙĦÙĦØ¥
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.